F3 adds attention-guided noise to adversarial images so that large vision-language models produce answers that are much closer to their clean-image answers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
F3 adds attention-guided noise to adversarial images so that large vision-language models produce answers that are much closer to their clean-image answers.